Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning

1 code implementation • 28 Mar 2022 • Cheng Liu, Erik-Jan van Kampen, Guido C. H. E. de Croon

Enabling the capability of assessing risk and making risk-aware decisions is essential to applying reinforcement learning to safety-critical robots like drones.

Distributional Reinforcement Learning Drone navigation +3

Soft Actor-Critic Deep Reinforcement Learning for Fault Tolerant Flight Control

1 code implementation • 16 Feb 2022 • Killian Dally, Erik-Jan van Kampen

Fault-tolerant flight control faces challenges, as developing a model-based controller for each unexpected failure is unrealistic, and online learning methods can handle limited system complexity due to their low sample efficiency.

reinforcement-learning Reinforcement Learning (RL)

On Approximate Dynamic Programming with Multivariate Splines for Adaptive Control

no code implementations • 30 Jun 2016 • Willem Eerland, Coen de Visser, Erik-Jan van Kampen

We introduce a local forget factor capable of preserving the continuity of the simplex splines.